Commit Graph

3 Commits

Author SHA1 Message Date
Joydeep Biswas fc826c5780 CUDA Cleanup
* All Cuda* objects now take in a ContextImpl* during
  construction, and save the context instead of individual
  handles.
* Since we no longer use the legacy default stream, we need to
  explicitly synchronize the stream before performing GPU->CPU
  transfers, and CudaBuffer is responsible for such synchronization
  when asked to perform GPU to CPU transfers.
* Remove all manual syncs and relegate syncing to CudaBuffer
  before performing GPU to CPU transfers.

Change-Id: Ic73cb24174a1e09842827323280e90241716cc20
2022-09-19 10:02:53 -05:00
Sameer Agarwal 6ab435d774 Fix a missing CERES_NO_CUDA guard
Also run format_all.sh.

Change-Id: I13902c1d3eb0d3a97548540fee13ec67c490a5ff
2022-08-14 16:58:09 -07:00
Joydeep Biswas c560bc2be5 CUDA CGNR, Part 3: CudaSparseMatrix
* Added CudaSparseMatrix to manage and operate on sparse matrices with
  cuSparse.
* Added tests for CudaSparseMatrix.
* Added a new sparse linear operator benchmark.

Change-Id: Id09df46de3b40be1f14441528088b54dab5844af
2022-08-14 18:48:55 -05:00